Dap-FL: Federated Learning Flourishes by Adaptive Tuning and Secure Aggregation

Practical Secure Aggregation for Federated Learning on User-Held Data

Secure Aggregation protocols allow a collection of mutually distrust parties, each holding a private value, to collaboratively compute the sum of those values without revealing the values themselves. We consider training a deep neural network in the Federated Learning model, using distributed stochastic gradient descent across user-held training data on mobile devices, wherein Secure Aggregatio...

Learning Adaptive Parameter Tuning for Image Processing

The non-stationary nature of image characteristics calls for adaptive processing, based on the local image content. We propose a simple and flexible method to learn local tuning of parameters in adaptive image processing: we extract simple local features from an image and learn the relation between these features and the optimal filtering parameters. Learning is performed by optimizing a user d...

Tuning Protein Aggregation Pathways by Charges

Design of A Self-Tuning Adaptive Power System Stabilizer

Power system stabilizers (PSSs) must be capable of providing appropriate stabilization signals over abroad range of operating conditions and disturbances. The main idea of this paper is changing aclassic PSS (CPSS) to an adaptive PSS using genetic algorithm. This new genetic algorithm based onadaptive PSS (GAPSS) improves power system damping, considerably. The controller design issue isformula...

Aggregation in Federated Databases: The DOK Approach

This paper addresses the design of the DOK security service allowing the enforcement of both local and federated policies. The former are those policies which relate to local databases, whereas the latter speci es the aggregation rules that govern the access to data aggregates which reside in di erent databases. In this paper we describe the component of the DOK security service which enforces ...